Basic and deep learning models in remote sensing of soil organic carbon estimation: A brief review

Abstract Understanding soil organic carbon (SOC) is critical to, among others, atmospherics and terrestrial carbon balance and climate change mitigation. This has necessitated development of novel analytical approaches to determine SOC. The use of neural network (NN) models for analysis of landscape biophysical and biochemical properties based on remotely sensed data has become popular in the last decade. This has been facilitated by the proliferation of “big data” from earth observation systems as well as the advances in machine learning (ML). Specifically, the use of traditional neural networks (TNN) and transition to deep learning (DL) frameworks offers considerable improvement in the performance and accuracy of SOC retrieval from remotely sensed data. This paper seeks to provide a brief review on the use of TNN and DL-based remote sensing strategies in SOC estimation, with focus on the progression, application, potential and limitations. The review concludes by providing major challenges impeding the wide adoption of DL frameworks in remote sensing applications of SOC, as well as the potential future research direction.